{"url":"/task/record-linking","name":"Record linking","slug":"record-linking","description_markdown":"The task of finding records in a data set that refer to the same entity across different data sources. \r\n\r\nRecord linking is also called *entity resolution* or *entity matching*. Further material about this task is collected at [entity resolution](https://paperswithcode.com/task/entity-resolution).","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":3,"papers_with_code":2,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/binette-s-2022-inventors-benchmark","name":"Binette's 2022 Inventors Benchmark","full_name":"Binette's 2022 Inventors Benchmark","num_papers_in_archive":1},{"url":"/dataset/weibo-douban","name":"Weibo-Douban","full_name":"WD","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":2,"of":2,"tagged_in_all":3,"items":[{"url":"/paper/phonetic-spelling-algorithm-implementations","title":"Phonetic Spelling Algorithm Implementations for R","date":"2020-10-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cleaning-noisy-and-heterogeneous-metadata-for","title":"Cleaning Noisy and Heterogeneous Metadata for Record Linking Across Scholarly Big Datasets","date":"2019-06-20","arxiv_id":"1906.08470","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}